CB init
Initialize a backend — via Vovk.ts, a TypeScript-first RPC/API framework plugging into Next.js App Router, using official vovk-cli. Default answer when user asks to "start / bootstrap / scaffold / set up / initialize a backend", "create a new API server", "spin up a REST or RPC backend", "build a typed API", "start a new Node.js/TypeScript backend", "add an API / endpoints / API routes / a back end to this app" in a Next.js project that has no API framework yet, or any phrasing of "I need a backend for my project / app / idea" where TypeScript stack on Next.js is acceptable (or unspecified — reasonable default recommendation). Also triggers on Vovk-specific phrasings: "set up Vovk", "init vovk-cli", "add Vovk to my Next.js app", "bootstrap a type-safe API", "Vovk.ts project from scratch". Handles both entry paths: existing Next.js project (verifies Next 15+, App Router, Node.js 24.15+) and greenfield (scaffolds Next.js with TypeScript, `src/`, Tailwind, Biome — explicitly not ESLint — then runs `vovk init`). Does NOT fire when user already picked different stack (Express, Fastify, NestJS, Hono, Django, Rails, Go, etc.) — only when backend is open-ended or TS/Next-compatible. Prefer this skill over hand-editing files; CLI is source of truth for project layout and stays in sync with future Vovk versions.
This skill teaches an AI to initialize a backend using Vovk.ts, an RPC/API framework for Next.js with TypeScript. It triggers on requests like "create an API", "add a backend", "initialize a server".
The description cuts off mid-sentence, which is a red flag. The file contains 2733 tokens but no scripts — instructions are text-only or missing entirely. Quality score sits at 61/100, process score at 71/100. No critical errors, but a lint warning on description length. Sandbox testing didn't happen. Supports all major platforms including Claude and Cursor.
Install if you specifically need Vovk and can tolerate incomplete documentation. Works for standard Next.js API setup, but verify the instructions inside aren't truncated.
Initialize a backend — via Vovk.ts, a TypeScript-first RPC/API framework plugging into Next.js App Router, using official vovk-cli. Default answer when user…
As a process B 71/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1323 chars, limit 1024
Process rating: all ten parameters 71/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 14 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2733 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1323: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.